Evaluation sources/LiveBench Data Analysis
ObservingProfessional work
LiveBench Data Analysis
LiveBench · Public model evaluation results from LiveBench Data Analysis.
Model results from this source
| GPT-6 Astra | 82.973333 | 83.0 | 2026-06-25 |
| GPT-6.1 Sol | 82.659333 | 82.7 | 2026-06-25 |
| Muse Wonder | 81.617333 | 81.6 | 2026-06-25 |
| GPT-5.5 | 81.575667 | 81.6 | 2026-06-25 |
| GPT-6 Sol | 81.189333 | 81.2 | 2026-06-25 |
| Claude Fable 5 | 80.537667 | 80.5 | 2026-06-25 |
| Claude Opus 5.5 | 80.307 | 80.3 | 2026-06-25 |
| Claude Fable 5.1 | 80.275667 | 80.3 | 2026-06-25 |
| GPT-5.6 Sol | 79.840667 | 79.8 | 2026-06-25 |
| Muse Spark 1.3 | 79.565333 | 79.6 | 2026-06-25 |
| DeepSeek V4 Flash 0731 | 79.327333 | 79.3 | 2026-06-25 |
| GPT-5.4 | 79.313333 | 79.3 | 2026-06-25 |
| GPT-5.6 Terra | 79.306667 | 79.3 | 2026-06-25 |
| DeepSeek V4.1 Flash | 79.253333 | 79.3 | 2026-06-25 |
| DeepSeek V4 Pro 0813 | 79.243333 | 79.2 | 2026-06-25 |
| Kimi K3 | 78.733667 | 78.7 | 2026-06-25 |
| Claude Sonnet 5.5 | 78.62 | 78.6 | 2026-06-25 |
| Gemini 3.1 Pro Preview | 78.541333 | 78.5 | 2026-06-25 |
| Qwen3.8 Max | 78.413 | 78.4 | 2026-06-25 |
| Claude Opus 4.7 | 78.263667 | 78.3 | 2026-06-25 |
| GPT-5.2 | 78.163333 | 78.2 | 2026-06-25 |
| GPT-5.6 Luna | 78.033333 | 78.0 | 2026-06-25 |
| Claude Sonnet 4.6 | 77.946 | 77.9 | 2026-06-25 |
| Grok 4.7 | 76.883333 | 76.9 | 2026-06-25 |
| Mistral Large 4 | 76.541667 | 76.5 | 2026-06-25 |
| Muse Spark 1.2 | 76.458333 | 76.5 | 2026-06-25 |
| GLM-5.3 Flash | 76.401 | 76.4 | 2026-06-25 |
| MiniMax-M3 | 76.166333 | 76.2 | 2026-06-25 |
| Claude Opus 5 | 74.550333 | 74.6 | 2026-06-25 |
| DeepSeek V4 Pro | 74.537667 | 74.5 | 2026-06-25 |
| Claude Opus 4.5 | 74.441667 | 74.4 | 2026-06-25 |
| Grok 4.6 | 73.857 | 73.9 | 2026-06-25 |
| GLM-5.2 | 73.739667 | 73.7 | 2026-06-25 |
| GPT-6 Luna | 73.369667 | 73.4 | 2026-06-25 |
| Grok 4.5 | 73.037667 | 73.0 | 2026-06-25 |
| Inkling | 72.778 | 72.8 | 2026-06-25 |
| Claude Haiku 5.5 | 72.753 | 72.8 | 2026-06-25 |
| Muse Spark 1.1 | 72.548 | 72.5 | 2026-06-25 |
| Qwen3.7 Max | 71.786 | 71.8 | 2026-06-25 |
| Claude Sonnet 5 | 71.740667 | 71.7 | 2026-06-25 |
| Grok Build 0.1 | 70.794 | 70.8 | 2026-06-25 |
| GPT-5.4 mini | 70.785667 | 70.8 | 2026-06-25 |
| Qwen3.6 27B | 70.426667 | 70.4 | 2026-06-25 |
| GLM 5.3 | 70.244333 | 70.2 | 2026-06-25 |
| Qwen3.6 Plus | 69.911667 | 69.9 | 2026-06-25 |
| Claude Opus 4.6 | 69.893 | 69.9 | 2026-06-25 |
| DeepSeek V4 Flash | 68.023 | 68.0 | 2026-06-25 |
| Claude Opus 4.8 | 66.033333 | 66.0 | 2026-06-25 |
| Kimi K2.6 | 65.134333 | 65.1 | 2026-06-25 |
| Gemini 3.6 Flash | 62.999333 | 63.0 | 2026-06-25 |
| Kimi K2.7 Code | 62.657333 | 62.7 | 2026-06-25 |
| Grok 4.3 | 55.772667 | 55.8 | 2026-06-25 |
| Nemotron 3 Ultra 550B A55B | 54.456667 | 54.5 | 2026-06-25 |
| Gemini 3.8 Flash | 54.005667 | 54.0 | 2026-06-25 |
| Gemini 3.5 Flash Lite | 53.249667 | 53.2 | 2026-06-25 |